hsa-test3萤石餐饮行业智能巡检技能。通过设备抓图 + 智能体分析接口，实现对餐厅/厨房场景的 AI 巡检，包括地面卫生、动火离人、垃圾桶状态、货品存放和口罩佩戴等关键指标。
Install via ClawdBot CLI:
clawdbot install shuanhu95/hsa-test3Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://open.ys7.com/help/81Calls external URL not in known-safe list
https://opencapture.ys7.com/...AI Analysis
The skill communicates only with documented Ezviz (萤石) APIs for legitimate device image capture and AI analysis, consistent with its stated restaurant inspection purpose. While it sends images to external servers, this is expected functionality for cloud-based AI analysis, and no credential harvesting or hidden instructions were found. The automatic token management is transparent and doesn't persist sensitive data.
Audited Apr 16, 2026 · audit v1.0
Generated May 12, 2026
连锁餐饮企业通过本技能对旗下多家门店进行统一的AI智能巡检，自动检查地面卫生、动火离人等关键指标，降低管理成本，确保各门店食品安全标准一致。
企事业单位食堂利用本技能实时监测后厨明火离人、地面湿滑等高风险因素，自动告警，提升安全管理效率，减少人为疏忽。
外卖平台或第三方监管机构使用本技能对外卖商家的厨房进行远程巡检，监控食材存放、员工口罩佩戴等合规项，提升外卖食安透明度。
政府部门或食药监机构利用本技能对餐饮场所进行随机在线抽查，通过AI分析取证，提高监管覆盖面和效率。
提供按门店/设备数定期订阅的AI巡检服务，客户无需维护硬件和算法，按月或年付费，降低使用门槛。
为大型连锁餐饮或政府机构定制化部署AI巡检系统，包括设备安装、系统集成和运维支持，一次性项目收费加后续维护。
基于AI巡检积累的数据，定期生成食品安全趋势分析报告、合规评分等增值内容，向客户额外收费。
💬 Integration Tip
技能提供Python脚本和命令行接口，只需配置环境变量和运行命令即可快速接入，建议从单个设备试点开始。
Scored Jun 29, 2026
Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring.
Automates system health monitoring, temp file cleanup, memory deduplication and summarization, with detailed logging for OpenClaw maintenance.
Surf forecast decision engine. Outputs surfable conditions for agent alerting.
Incident Commander Skill
Monitors OpenClaw cron job health, identifies failures, timeouts, and delivery issues.
Full stack observability - reproducibility, lineage, monitoring, alerting